[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"tag-policy-optimization":3},{"tag":4,"articles":10},{"id":5,"name":6,"slug":7,"article_count":8,"description_zh":9,"description_en":9},"29f3ff9f-f801-4442-a4d2-f0cb97fc39e4","policy optimization","policy-optimization",2,null,[11,20],{"id":12,"slug":13,"title":14,"summary":15,"category":16,"image_url":17,"cover_image":17,"language":18,"created_at":19},"19f116fd-02dd-4a7d-9638-75a3bb70cae2","bounded-ratio-reinforcement-learning-ppo-en","Why Bounded Ratio RL Replaces PPO's Clipped Objective","BRRL gives PPO a cleaner theory, with BPO and GBPO aiming for more stable policy updates in control and LLM fine-tuning.","research","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776751796218-p4in.png","en","2026-04-21T06:09:40.318224+00:00",{"id":21,"slug":22,"title":23,"summary":24,"category":16,"image_url":25,"cover_image":25,"language":18,"created_at":26},"d1bbd868-15d4-459c-9e2b-2626c779b4ef","prerl-training-llms-in-pre-train-space-en","PreRL: Training LLMs in pre-train space","PreRL shifts reinforcement learning from P(y|x) to P(y), using reward-driven updates in pre-train space to improve reasoning and exploration.","https:\u002F\u002Fxxdpdyhzhpamafnrdkyq.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Fcovers\u002Finline-1776319621187-aig1.png","2026-04-16T06:06:38.24406+00:00"]